CNN

김동환·2023년 3월 21일
0

AI_tech_5기

목록 보기
8/18
post-custom-banner

AlexNet

  • ReLU activation
  • GPI implementations
  • Local response normalization, Overlapping pooling

ReLU

  • Preserves properties of linear models

  • Easy to optimize

  • Overcom the vanishing grad problem

    VGGNet

  • Increasing depth with 3x3 filters

  • 1x1 conv for fc layers

  • Dropout 0.5

    Why 3X3 convolution?

  • 파리미터 수 측면에서 이득

  • 더 깊게 쌓을 수 있음

GoogLeNet

  • network in network (NiN) with inception blocks

inception blocks

  • reduce the # of params
  • 1x1 conv = channel wise dimension reduction

ResNet

  • The deeper the nn is, the harder to train the nn
  • Add an identity map(skip connection) afther nonlinear activations

DenseNet

  • instead addition, use concatenation
  • However, repeated concatenation can lead to increasing # of channels(params)
  • DenseNet introduces transition block to solve this problem

Transition Block

  • BN -> 1x1 conv(reduction) -> 2x2 Avg pooling
profile
AI Engineer
post-custom-banner

0개의 댓글